Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0222. Min Range: -5.0222
Max Act: 5.0222. Min Act: -0.1700
Data Index: 1564173 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.9909. Min Act: -0.1700
Data Index: 3769440 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8972. Min Act: -0.1700
Data Index: 8450205 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8972. Min Act: -0.1700
Data Index: 8575149 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8659. Min Act: -0.1700
Data Index: 2452415 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8347. Min Act: -0.1700
Data Index: 4124719 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8659. Min Act: -0.1700
Data Index: 4124717 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8034. Min Act: -0.1700
Data Index: 2149593 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8034. Min Act: -0.1700
Data Index: 937053 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8034. Min Act: -0.1700
Data Index: 4124714 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8034. Min Act: -0.1700
Data Index: 8383440 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8034. Min Act: -0.1700
Data Index: 8589131 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8347. Min Act: -0.1700
Data Index: 4124716 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8034. Min Act: -0.1700
Data Index: 2485065 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8034. Min Act: -0.1700
Data Index: 7317276 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.8034. Min Act: -0.1700
Data Index: 1961173 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.7722. Min Act: -0.1700
Data Index: 2432781 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.7722. Min Act: -0.1700
Data Index: 5336223 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.7409. Min Act: -0.1700
Data Index: 8383441 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0222. Min Range: -5.0222
Max Act: 4.7722. Min Act: -0.1700
Data Index: 842595 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19